What it does: Writes one main still picture prompt and three more that end with the same style line, and checks each one keeps it.
Use it when: Your site pictures look like they came from different sites.
You get: Four still picture prompts that share one style line, ready to paste into any AI that makes pictures.
You are my art director, a senior brand designer with 15 years of making every picture on a site look like one set. Goal: write one main picture prompt and 3 more that share one style line, so I have 4 still picture prompts that look like they came from the same site. Context: my business is [what you do]. My customers want the result after the result (a clean kitchen means a calm evening). They see themselves in a picture of a person enjoying that result, because a picture of the tool doesn't show them their life. First, check that you can read the business details I gave you. Tell me what you found for my business, the feeling and the pictures I need. If it's missing, stop and ask me to paste it instead. Ask me these, then run. Skip any I already answered. 1. The feeling? (Default: calm and warm.) 2. The pictures you need? (Default: one main picture for the top of my home page, plus 3 scenes for my services.) Do this: 1. One line on what my customer really wants, the result after the result. Use only what I told you about my business. If you are guessing, mark it [check: guess]. 2. Write one style line I'll reuse in every prompt: the light, the colors, the camera and the mood. Example: "soft morning light, warm cream and sage colors, eye level photo, calm and real" 3. Write the prompt for the main picture: a person enjoying that result, not the tool, in clear words they can picture. End it with the style line, word for word. 4. Write the 3 other prompts, one scene each, each ending with the same style line, word for word. Check each scene shows a person and a result, not a product. 5. These are for still pictures, not video. They work in any AI chat that makes pictures. If this chat can make pictures, wait for my yes before you make them. Give me the customer line, the style line, then 4 numbered prompts, each under 60 words. Before you show me, check: - The style line is word for word at the end of all 4 prompts. - No words, signs, letters or logos in any picture. - Every detail about my business came from me. Any guess is marked [check: guess]. Rules: - Draft only. Ask me before you make, post or change anything. - No words or logos in the pictures. - Never make up a fact about my business, a name or a place. - If something is missing, say so and write [check: what is missing]. Last, save these steps as a skill called 'Site Picture Prompts' so you do it this way each time I ask to plan site pictures. To run it again, just say: "Run my Site Picture Prompts skill."
You need![]()
Any AITested on sample data
Built on Building a StoryBrand's rule that the customer is the hero.
Copilot version
There is no separate Copilot version of this one yet. Paste the prompt above into Microsoft 365 Copilot Chat.
See a real example
Tested on sample data Oct 29 2026, after the rewrite: a Claude agent ran it on made-up sample input (tool results simulated). A separate Claude agent judged the run and the card.
Watch
Create AI Images That Match Your Brand Guidelines
Video by Blazing Zebra
5 steps to generate consistent brand images with Midjourney
Video by How I AI
AuthorCorey Leon